To study the neural circuitry, the action of one cell under the context of others, one would precisely measure and perturb specific neuronal populations and molecules in behaving animals who are specifically engaged in performing the computation or function of interest. The dataset of millions of neurons firing together underlying a behavior is required to develop and refine theories (hypotheses) explaining animal behavior in terms of brain physiology. The lab focuses on developing novel genetically encoded indicators based on fluorescence proteins and chemical dyes, especially focusing on direct and specific measurement of myriad input signals with needed spatial and temporal resolutions. In this talk, I will discuss our recent progress in developing genetically encoded indicators for neuromodulators using machine-learning based single-cell screening. I will discuss the design, characterization, and applications of these genetically encoded indicators, especially serotonin probes, for both in vivo imaging and drug discovery. In combination with calcium imaging and optogenetics, these sensors are well poised to permit direct functional analysis of how the spatiotemporal coding of neural input signaling mediates the plasticity and function of target circuits.